今天15:00 | ICML-5 不见不散！

点击蓝字

关注我们

AI TIME欢迎每一位AI爱好者的加入！

9月23日 15:00~20:30

AI TIME特别邀请了多位PhD，带来ICML-5！

哔哩哔哩直播通道

扫码关注AITIME哔哩哔哩官方账号

观看直播

链接：https://live.bilibili.com/21813994

15:00-17:00

★ 嘉宾介绍 ★

邓维建：

澳洲国立大学二年级在读博士，在 Prof. Stephen Gould  和 Dr. Liang Zheng 指导下进行模型泛化能力研究。

个人主页https://weijiandeng.xyz。

报告题目：

旋转预测能够告诉我们分类器

准确度的哪些信息？

内容简介：

Understanding classifier decision under novel environments is central to the community, and a common practice is evaluating it on labeled test sets. However, in real-world testing, image annotations are difficult and expensive to obtain, especially when the test environment is changing. A natural question then arises: given a trained classifier, can we evaluate its accuracy on varying unlabeled test sets? In this work, we train semantic classification and rotation prediction in a multi-task way. On a series of datasets, we report an interesting finding, i.e., the semantic classification accuracy exhibits a strong linear relationship with the accuracy of the rotation prediction task (Pearson’s Correlation r > 0.88). This finding allows us to utilize linear regression to estimate classifier performance from the accuracy of rotation prediction which can be obtained on the test set through the freely generated rotation labels.

刘旭彤：

香港中文大学在读博士生，师从John C.S. Lui, 研究兴趣包括强化学习、在线学习理论，特别是组合多臂老虎机(combinatorial multi-armed badnit)的算法设计、理论分析和在社交网络中的应用。

个人主页：https://xutongliu.me/.

报告题目：

利用随机游走算法的多层

网络探索：从离线优化到在线学习

内容简介：

Multi-layered network exploration (MuLaNE) problem is an important problem abstracted from many applications. In MuLaNE, there are multiple network layers where each node has an importance weight and each layer is explored by a random walk. The MuLaNE task is to allocate total random walk budget B into each network layer so that the total weights of the unique nodes visited by random walks are maximized. We systematically study this problem from offline optimization to online learning. For the offline optimization setting where the network structure and node weights are known, we provide greedy based constant-ratio approximation algorithms for overlapping networks, and greedy or dynamic-programming based optimal solutions for non-overlapping networks. For the online learning setting, neither the network structure nor the node weights are known initially. We adapt the combinatorial multi-armed bandit framework and design algorithms to learn random walk related parameters and node weights while optimizing the budget allocation in multiple rounds, and prove that they achieve logarithmic regret bounds. Finally, we conduct experiments on a real-world social network dataset to validate our theoretical results.

滕佳烨：

清华大学交叉信息研究院二年级博士生，导师为袁洋助理教授。主要研究方向是神经网络泛化理论，以及统计理论与机器学习的结合，包括因果推断、共形预测等。

报告题目：

T-SCI: 基于Cox-MLP模型的

二阶段共形预测

内容简介：

It is challenging to deal with censored data, where we only have access to the incomplete information of survival time instead of its exact value.

Fortunately, under linear predictor assumption, people can obtain guaranteed coverage for the confidence band of survival time using methods like Cox Regression. However, when relaxing the linear assumption with neural networks (e.g., Cox-MLP), we lose the guaranteed coverage. To recover the guaranteed coverage without linear assumption, we propose two algorithms based on conformal inference under strong ignorability assumption. In the first algorithm WCCI, we revisit weighted conformal inference and introduce a new non-conformity score based on partial likelihood. We then propose a two-stage algorithm T-SCI, where we run WCCI in the first stage and apply quantile conformal inference to calibrate the results in the second stage. Theoretical analysis shows that T-SCI returns guaranteed coverage under milder assumptions than WCCI. We conduct extensive experiments on synthetic data and real data using different methods, which validate our analysis.

谢肖飞：

目前是新加坡南洋理工大学的校长博士后，曾毕业于天津大学。主要研究方向包括软件工程、安全以及人工智能领域，并在相关领域的顶级期刊与会议上发表论文多篇，包括 ICSE，ISSTA，FSE，ASE, TSE，TOSEM，IJCAI，ECCV，ICCV，ICLR, ICML，NeurIPS，CCS，AAAI，TIFS，TDSC等。其中那个两次获得 ACM SIGSOFT Distinguished Paper Awards (FSE'16, ASE'19).

报告题目：

基于模型分析的循环神经网络自动修复

内容简介：

Deep neural networks are vulnerable to adversarial attacks. Due to their black-box nature, it is rather challenging to interpret and properly repair these incorrect behaviors. This paper focuses on interpreting and repairing the incorrect behaviors of Recurrent Neural Networks (RNNs). We propose a lightweight model-based approach (RNNRepair) to help understand and repair incorrect behaviors of an RNN. Specifically, we build an influence model to characterize the stateful and statistical behaviors of an RNN over all the training data and to perform the influence analysis for the errors. Compared with the existing techniques on influence function, our method can efficiently estimate the influence of existing or newly added training samples for a given prediction at both sample level and segmentation level. Our empirical evaluation shows that the proposed influence model is able to extract accurate and understandable features. Based on the influence model, our proposed technique could effectively infer the influential instances from not only an entire testing sequence but also a segment within that sequence. Moreover, with the sample-level and segment-level influence relations, RNNRepair could further remediate two types of incorrect predictions at the sample level and segment level.

19:30-20:30

李晓宇：

波士顿大学系统工程博士四年级学生，导师是Dr. Francesco Orabona。研究方向主要包括随机优化，机器学习理论。

报告题目：

随机梯度下降与指数步长及余弦步长

内容简介：

Stochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for tuning the step sizes have been proposed, ranging from coordinate-wise approaches (a.k.a. “adaptive” step sizes) to sophisticated heuristics to change the step size in each iteration. In this paper, we study two step size schedules whose power has been repeatedly confirmed in practice: the exponential and the cosine step sizes. For the first time, we provide theoretical support for them proving convergence rates for smooth non-convex functions, with and without the Polyak-Łojasiewicz (PL) condition. Moreover, we show the surprising property that these two strategies are adaptive to the noise level in the stochastic gradients of PL functions. That is, contrary to polynomial step sizes, they achieve almost optimal performance without needing to know the noise level nor tuning their hyperparameters based on it. Finally, we conduct a fair and comprehensive empirical evaluation of real-world datasets with deep learning architectures. Results show that, even if only requiring at most two hyperparameters to tune, these two strategies best or match the performance of various finely-tuned state-of-the-art strategies.

郭文博：

宾州州立大学博士，研究方向主要是机器学习和安全， 并在相关领域的顶级期刊与会议上发表论文多篇，包括 ICML，NeurIPS，CCS，USENIX Security, NDSS等。获得 ACM CCS Outstanding Paper Awards, 2018, IBM PhD. Fellowship Award, 2020, 以及Facebook/Baidu Ph.D. Fellowship finalists, 2020.

报告题目：

对抗深度强化学习策略的训练和理论保障

内容简介：

In a two-player deep reinforcement learning task, recent work shows an attacker could learn an adversarial policy that triggers a target agent to perform poorly and even react in an undesired way. However, its efficacy heavily relies upon the zero-sum assumption made in the two-player game. In this work, we propose a new adversarial learning algorithm. It addresses the problem by resetting the optimization goal in the learning process and designing a new surrogate optimization function. Our experiments show that our method significantly improves adversarial agents’ exploitability compared with the state-of-art attack. Besides, we also discover that our method could augment an agent with the ability to abuse the target game’s unfairness. Finally, we show that agents adversarially retrained against our adversarial agents could obtain stronger adversary-resistance.

# 今日视推荐 #

直播结束后我们会邀请讲者在微信群中与大家答疑交流，请添加“AI TIME小助手（微信号：AITIME_HY）”，回复“icml”，将拉您进“AI TIME ICML 会议交流群”！

AI TIME微信小助手

主       办：AI TIME 

合作媒体：学术头条、AI 数据派

合作伙伴：智谱·AI、中国工程院知领直播、学堂在线、学术头条、biendata、 Ever链动

AI TIME欢迎AI领域学者投稿，期待大家剖析学科历史发展和前沿技术。针对热门话题，我们将邀请专家一起论道。同时，我们也长期招募优质的撰稿人，顶级的平台需要顶级的你，

请将简历等信息发至yun.he@aminer.cn！

微信联系:AITIME_HY

AI TIME是清华大学计算机系一群关注人工智能发展，并有思想情怀的青年学者们创办的圈子,旨在发扬科学思辨精神，邀请各界人士对人工智能理论、算法、场景、应用的本质问题进行探索，加强思想碰撞，打造一个知识分享的聚集地。

更多资讯请扫码关注

我知道你“在看”哟～

点击 阅读原文 了解更多精彩